average local variance

Hi, I need to compute the diagonal error weight matrix (W), where W(i,i) measure the average local variance of pixels with gray level i. Can u please help me regarding this. i will be grateful.

[Oleg Komarov]

Not enough info: http://www.mathworks.com/matlabcentral/answers/6200-tutorial-how-to-ask-a-question-on-answers-and-get-a-fast-answer

Answer 1

[Image Analyst]

Again, I'm not sure what this means or if it is really what you want but I think it's what you described.

clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
imtool close all;  % Close all imtool figures.
clear;  % Erase all existing variables.
workspace;  % Make sure the workspace panel is showing.
fontSize = 20;

% Read in a standard MATLAB gray scale demo image.
folder = fullfile(matlabroot, '\toolbox\images\imdemos');
baseFileName = 'cameraman.tif';
fullFileName = fullfile(folder, baseFileName);
% Get the full filename, with path prepended.
fullFileName = fullfile(folder, baseFileName);
if ~exist(fullFileName, 'file')
  % Didn't find it there.  Check the search path for it.
  fullFileName = baseFileName; % No path this time.
  if ~exist(fullFileName, 'file')
    % Still didn't find it.  Alert user.
    errorMessage = sprintf('Error: %s does not exist.', fullFileName);
    uiwait(warndlg(errorMessage));
    return;
  end
end
grayImage = imread(fullFileName);
% Get the dimensions of the image.  
% numberOfColorBands should be = 1.
[rows columns numberOfColorBands] = size(grayImage);
% Display the original gray scale image.
subplot(2, 3, 1);
imshow(grayImage, []);
title('Original Grayscale Image', 'FontSize', fontSize);
% Enlarge figure to full screen.
set(gcf, 'units','normalized','outerposition',[0 0 1 1]);
% Give a name to the title bar.
set(gcf,'name','Demo by ImageAnalyst','numbertitle','off') 

% Calculate the standard deviation image.
sdImage = stdfilt(grayImage);
% Display the image.
subplot(2, 3, 2);
imshow(sdImage, []);
title('Std. Dev. Image', 'FontSize', fontSize);

% Calculate the variance image.
varianceImage = sdImage .^2;
% Display the image.
subplot(2, 3, 3);
imshow(varianceImage, []);
title('Variance Image', 'FontSize', fontSize);

% Calculate the mean of the variance image in a 3x3 region.
% Basically this is a blurred version of it.
meanVarianceImage = conv2(varianceImage, ones(3)/9);
% Display the image.
subplot(2, 3, 4);
imshow(meanVarianceImage, []);
title('Mean Variance Image', 'FontSize', fontSize);

for gl = 0:255
  % Find pixels in the original image with this gray level.
  matchingIndexes = (grayImage == gl);
  % Get the mean of only those pixels from the mean variance image.
  W(gl+1) = mean(meanVarianceImage(matchingIndexes));
end
% Plot W
subplot(2, 3, 5);
plot(W);
grid on;
title('Plot of W', 'FontSize', fontSize);
xlabel('Gray Level', 'FontSize', fontSize);

[Walter Roberson]

dinial utami comments

I like it thanks

Answer 2

[Image Analyst]

I'm not sure what W is. But you can use stdfilt() to get the st.dev. in a local window of an image. Square it to get the variance. If you want the average of the 9 variances of the 9 pixels in a 3x3 neighborhood, then you can use imfilter() or conv2() with a kernel of ones(3)/9. Then you need to go through each gray level, extracting that mean variance, something like (maybe??? untested)

for gl = 0:255
  % Find pixels in the original image with this gray level.
  matchingIndexes = (imageArray == gl);
  % Get the mean of only those pixels from the mean variance image.
  W(gl+1) = mean(meanVarianceImage(matchingIndexes ));
end

[ismaiel]

I did not understand what you mean by the following sentence

Then you need to go through each gray level, extracting that mean variance.

Please give an example if possible

note i used function stdfilt(I),where I is an image and the result is zero matrix?why?

[Image Analyst]

No, it's not all zero - you're just not using [] to display in with imshow. See my other answer for a more complete demo.